metadata

base_model: nvidia/mit-b0
license: other
tags:
  - vision
  - image-segmentation
  - generated_from_trainer
model-index:
  - name: segformer-b0-finetuned-segments-SixrayKnife8-19-2024
    results: []

segformer-b0-finetuned-segments-SixrayKnife8-19-2024

This model is a fine-tuned version of nvidia/mit-b0 on the saad7489/SixraygunTest dataset. It achieves the following results on the evaluation set:

Loss: 0.6355
Mean Iou: 0.5008
Mean Accuracy: 0.7954
Overall Accuracy: 0.7906
Accuracy Bkg: nan
Accuracy Knife: 0.7186
Accuracy Gun: 0.8722
Iou Bkg: 0.0
Iou Knife: 0.6915
Iou Gun: 0.8110

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 5
eval_batch_size: 5
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Bkg	Accuracy Knife	Accuracy Gun	Iou Knife	Iou Gun
0.7945	1.4286	20	0.7932	0.5023	0.8446	0.8389	nan	0.7531	0.9361	0.7186	0.7883
0.7385	2.8571	40	0.7324	0.5150	0.8445	0.8404	nan	0.7787	0.9103	0.7375	0.8074
0.7139	4.2857	60	0.7152	0.5033	0.8256	0.8200	nan	0.7358	0.9155	0.7072	0.8027
0.7405	5.7143	80	0.6747	0.4953	0.7972	0.7917	nan	0.7078	0.8866	0.6785	0.8075
0.6666	7.1429	100	0.6442	0.4937	0.7919	0.7860	nan	0.6964	0.8874	0.6723	0.8089
0.6357	8.5714	120	0.6210	0.4957	0.7874	0.7823	nan	0.7059	0.8688	0.6794	0.8076
0.6548	10.0	140	0.6355	0.5008	0.7954	0.7906	nan	0.7186	0.8722	0.6915	0.8110

Framework versions

Transformers 4.42.4
Pytorch 2.3.1+cu121
Datasets 2.21.0
Tokenizers 0.19.1